Home // International Journal On Advances in Systems and Measurements, volume 16, numbers 1 and 2, 2023 // View article
Authors:
Michael Weber
Tobias Weiss
Franck Gechter
Reiner Kriesten
Keywords: Artificial Intelligence; Augmented Reality; Advanced Driver Assistance Systems; Visual Simultaneous Localization and Mapping; Oriented FAST and BRIEF
Abstract:
Taking advantage of Advanced Driver Assistance Systems (ADAS) testing in simulation and reality, this paper presents a new approach to using Augmented Reality (AR) to test ADAS. Our procedure creates a link between simulation and reality besides existing methods like Vehicle in the Loop (ViL) and should enable a faster development process for ADAS tests, which will become increasingly complex. High computer power is needed for complex automotive environmental conditions, such as high vehicle speed and fewer orientation points on a test track compared to AR applications inside a building. A three-dimensional model with accurate information about the urban test site is generated based on the combination of Image Segmentation (IS), Artificial Intelligence (AI) for object recognition, and Visual Simultaneous Localization and Mapping (vSLAM). The use of AI and IS aims to significantly improve performance, such as robustness, calculation speed, and accuracy for AR applications in complex automobiles. Another focus of this work is to make the relocalization stable even in low-texture environments.
Pages: 53 to 65
Copyright: Copyright (c) to authors, 2023. Used with permission.
Publication date: June 30, 2023
Published in: journal
ISSN: 1942-261x